Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “label quality”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

AutoPhaseNN: unsupervised physics-aware deep learning of 3D nanoscale Bragg coherent diffraction imaging

Abstract The problem of phase retrieval underlies various imaging methods from astronomy to nanoscale imaging. Traditional phase retrieval methods are iterative and are therefore computationally expensive. Deep learning (DL) models have been developed to either provide learned priors or completely replace phase retrieval. However, such models require vast amounts of labeled data, which can only be obtained through simulation or performing computationally prohibitive phase retrieval on experimental datasets. Using 3D X-ray Bragg coherent diffraction imaging (BCDI) as a representative technique, we demonstrate AutoPhaseNN, a DL-based approach which learns to solve the phase problem without labeled data. By incorporating the imaging physics into the DL model during training, AutoPhaseNN learns to invert 3D BCDI data in a single shot without ever being shown real space images. Once trained, AutoPhaseNN can be effectively used in the 3D BCDI data inversion about 100× faster than iterative phase retrieval methods while providing comparable image quality.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Galaxy Spin Classification. I. Z-wise versus S-wise Spirals with the Chirality Equivariant Residual Network

The angular momentum of galaxies (galaxy spin) contains rich information about the initial condition of the universe, yet it is challenging to efficiently measure the spin direction for the tremendous amount of galaxies that are being mapped by ongoing and forthcoming cosmological surveys. We present a machine-learning-based classifier for the Z-wise versus S-wise spirals, which can help to break the degeneracy in the galaxy spin direction measurement. The proposed chirality equivariant residual network (CE-ResNet) is manifestly equivariant under a reflection of the input image, which guarantees that there is no inherent asymmetry between the Z-wise and S-wise probability estimators. We train the model with Sloan Digital Sky Survey images, with the training labels given by the Galaxy Zoo 1 project. A combination of data augmentation techniques is used during the training, making the model more robust to be applied to other surveys. We find an ~30% increase in both types of spirals when Dark Energy Spectroscopic Instrument (DESI) images are used for classification, due to the better imaging quality of DESI. We verify that the ~7σ difference between the numbers of Z-wise and S-wise spirals is due to human bias, since the discrepancy drops to <1.8σ with our CE-ResNet classification results. We discuss the potential systematics relevant to future cosmological applications.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

A review of artificial intelligence applications in manufacturing operations

Abstract Artificial intelligence (AI) and machine learning (ML) can improve manufacturing efficiency, productivity, and sustainability. However, using AI in manufacturing also presents several challenges, including issues with data acquisition and management, human resources, infrastructure, as well as security risks, trust, and implementation challenges. For example, getting the data needed to train AI models can be difficult for rare events or costly for large datasets that need labeling. AI models can also pose security risks when integrated into industrial control systems. In addition, some industry players may be hesitant to use AI due to a lack of trust or understanding of how it works. Despite these challenges, AI has the potential to be extremely helpful in manufacturing, particularly in applications such as predictive maintenance, quality assurance, and process optimization. It is important to consider the specific needs and capabilities of each manufacturing scenario when deciding whether and how to use AI in manufacturing. This review identifies current developments, challenges, and future directions in AI/ML relevant to manufacturing, with the goal of improving understanding of AI/ML technologies available for solving manufacturing problems, providing decision‐support for prioritizing and selecting appropriate AI/ML technologies, and identifying areas where further research can yield transformational returns for the industry. Early experience suggests that AI/ML can have significant cost and efficiency benefits in manufacturing, especially when combined with the ability to capture enormous amounts of data from manufacturing systems.

Plathottam, Siby Jose↗
NASA NTRS2013

Parts Quality Management: Direct Part Marking via Data Matrix Symbols for Mission Assurance

A United States Government Accountability Office (GAO) review of twelve NASA programs found widespread parts quality problems contributing to significant cost overruns, schedule delays, and reduced system reliability. Direct part-marking with Data Matrix symbols could significantly improve the quality of inventory control and parts lifecycle management. This paper examines the feasibility of using 15 marking technologies for use in future NASA programs. A structural analysis is based on marked material type, operational environment (e.g., ground, suborbital, orbital), durability of marks, ease of operation, reliability, and affordability. A cost-benefits analysis considers marking technology (data plates, label printing, direct part marking) and marking types (two-dimensional machine-readable, human-readable). Previous NASA parts marking efforts and historical cost data are accounted for, including in-house vs. outsourced marking. Some marking methods are still under development. While this paper focuses on NASA programs, results may be applicable to a variety of industrial environments.

Moss, Chantrice↗
DOE OSTI2021

Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks : *Full/Regular Research Paper submission for the symposium CSCI-ISAI: Artificial Intelligence

We use a stable parallel approach to train Wasserstein Conditional Generative Adversarial Neural Networks (W-CGANs). The parallel training reduces the risk of mode collapse and enhances scalability by using multiple generators that are concurrently trained, each one of them focusing on a single data label. The use of the Wasserstein metric reduces the risk of cycling by stabilizing the training of each generator. We apply the approach on the CIFAR10 and the CIFAR100 datasets, two standard benchmark datasets with images of the same resolution, but different number of classes. Performance is assessed using the inception score, the Fréchet inception distance, and image quality. An improvement in inception score and Fréchet inception distance is shown in comparison to previous results obtained by performing the parallel approach on deep convolutional conditional generative adversarial neural networks (DC-CGANs). Weak scaling is attained on both datasets using up to 100 NVIDIA V100 GPUs on the OLCF supercomputer Summit.

Lupo Pasini, Massimiliano↗
DOE OSTI2024

Cryo2StructData: A Large Labeled Cryo-EM Density Map Dataset for AI-based Modeling of Protein Structures

The advent of single-particle cryo-electron microscopy (cryo-EM) has brought forth a new era of structural biology, enabling the routine determination of large biological molecules and their complexes at atomic resolution. The high-resolution structures of biological macromolecules and their complexes significantly expedite biomedical research and drug discovery. However, automatically and accurately building atomic models from high-resolution cryo-EM density maps is still time-consuming and challenging when template-based models are unavailable. Artificial intelligence (AI) methods such as deep learning trained on limited amount of labeled cryo-EM density maps generate inaccurate atomic models. To address this issue, we created a dataset called Cryo2StructData consisting of 7,600 preprocessed cryo-EM density maps whose voxels are labelled according to their corresponding known atomic structures for training and testing AI methods to build atomic models from cryo-EM density maps. Cryo2StructData is larger than existing, publicly available datasets for training AI methods to build atomic protein structures from cryo-EM density maps. We trained and tested deep learning models on Cryo2StructData to validate its quality showing that it is ready for being used to train and test AI methods for building atomic models.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2013

Parts Quality Management: Direct Part Marking of Data Matrix Symbol for Mission Assurance

A United States Government Accountability Office (GAO) review of twelve NASA programs found widespread parts quality problems contributing to significant cost overruns, schedule delays, and reduced system reliability. Direct part marking with Data Matrix symbols could significantly improve the quality of inventory control and parts lifecycle management. This paper examines the feasibility of using direct part marking technologies for use in future NASA programs. A structural analysis is based on marked material type, operational environment (e.g., ground, suborbital, Low Earth Orbit), durability of marks, ease of operation, reliability, and affordability. A cost-benefits analysis considers marking technology (label printing, data plates, and direct part marking) and marking types (two-dimensional machine-readable, human-readable). Previous NASA parts marking efforts and historical cost data are accounted for, including inhouse vs. outsourced marking. Some marking methods are still under development. While this paper focuses on NASA programs, results may be applicable to a variety of industrial environments.

Moss, Chantrice↗
DOE OSTI2023

Specifications and pre-production of n + -in-p large-format strip sensors fabricated in 6-inch silicon wafers, ATLAS18, for the Inner Tracker of the ATLAS Detector for High-Luminosity Large Hadron Collider

Abstract The ATLAS experiment is constructing new all-silicon inner tracking system for HL-LHC. The strip detectors cover the radial extent of 40 to 100 cm. A new approach is adopted to use p-type silicon material, making the readout in n + -strips, so-called n + -in-p sensors. This allows for enhanced radiation tolerance against an order of magnitude higher particle fluence compared to the LHC. To cope with varying hit rates and occupancies as a function of radial distance, there are two barrel sensor types, the short strips (SS) for the inner 2 and the long strips (LS) for the outer 2 barrel cylinders, respectively. The barrel sensors exhibit a square, 9.8 × 9.8 cm 2 , geometry, the largest possible sensor area from a 6-inch wafer. The strips are laid out in parallel with a strip pitch of 75.5 μm and 4 or 2 rows of strip segments. The strips are AC-coupled and biased via polysilicon resistors. The endcap sensors employ a “stereo-annulus” geometry exhibiting a skewed-trapezoid shapes with circular edges. They are designed in 6 unique shapes, R0 to R5, corresponding to progressively increasing radial extents and which allows them to fit within the petal geometry and the 6-inch wafer maximally. The strips are in fan-out geometry with an in-built rotation angle, with a mean pitch of approximately 75 μm and 4 or 2 rows of strip segments. The eight sensor types are labeled as ATLAS18xx where xx stands for SS, LS, and R0 to R5. According to the mechanical and electrical specifications, CAD files for wafer processing were laid out, following the successful designs of prototype barrel and endcap sensors, together with a number of optimizations. A pre-production was carried out prior to the full production of the wafers. The quality of the sensors is reviewed and judged excellent through the test results carried out by vendor. These sensors are used for establishing acceptance procedures and to evaluate their performance in the ATLAS collaboration, and subsequently for pre-production of strip modules and stave and petal structures.

Instruments & Instrumentation↗
DOE OSTI2022

Susceptibility of new soil organic carbon to mineralization during dry-wet cycling in soils from contrasting ends of a precipitation gradient

The persistence of soil organic carbon (SOC) is influenced by soil physicochemical properties, organic matter quality, and climatic conditions that govern its vulnerability to microbial activity. We compared the susceptibility of newly formed SOC to mineralization in two soils (Andosols) that developed under contrasting precipitation regimes. Soil from the high rainfall region (‘high rain ’) had higher SOC and lower iron concentrations than soils exposed to less rainfall (‘low rain ’). We amended soils with 13 C-labeled carbohydrates and measured the amount of substrate-derived SO 13 C mineralized when exposed to dry-wet cycling following months-long incubations. We hypothesized that susceptibility would differ due to iron content and mineralogy, initial SOC, substrate solubility (cellulose versus glucose amendment), and microbial substrate use efficiency (SUE). We found that SO 13 C was less susceptible to dry-wet cycling when more 13 C was assimilated into microbial biomass and co-localized with mineral surfaces than when co-localized with existing organo-mineral surfaces, according to microscale NanoSIMS imaging. Considerably less SO 13 C was susceptible to mineralization in the ferrihydrite-rich (low SOC) low rain soil than the leached (high SOC) high rain soil when C was added as either glucose (7.3-fold less C mineralized) or cellulose (15.2-fold less). Additionally, the SUE of glucose was comparable to cellulose in low rain soil where SO 13 C was less water soluble and coprecipitated with ferrihydrite, and used half as efficiently as cellulose in high rain soil. Our results show that the susceptibility of newly formed SOC to mineralization is modified by the effects of bioavailability on microbial metabolism and the availability of mineral surfaces for forming new organo-mineral complexes.

21 NanoSIMS↗
NASA NTRSDate not supplied

Curating AI-Ready Datasets for Equity and Environmental Justice: A Data-Centric AI Case Study

An equitable and environmentally just community is essentialin order to avoid disproportionate burden borne by vulnerablecommunities. This need becomes pressing in the aftermathof an extreme event such as disaster or hazard when it is diffi-cult for the governing bodies to implement resource allocationas per the need. Artificial Intelligence (AI) algorithms canhelp surface Equity and Environmental Justice (EEJ) issueswhen trained on EEJ datasets. However, curating AI-readyEEJ training datasets is challenging due to differences in fac-tors such as heterogeneity, resolution, modality, and level ofexpertise in labeling. Additionally, EEJ issues involve sensi-tive information where uncertainties and errors could degradethe performance of AI algorithms. For eg. Error in seasonalcrop yield information can highly affect the prediction of an-nual crop yield. To address these challenges, Data-centricAI (DCAI) methods are employed, which enhance AI algo-rithm performance even with limited training samples. DCAIprioritizes data quality, thereby reducing the adverse effectsof uncertainties and errors during the model training process.This research proposes a novel dataset and benchmark for an-alyzing the effect of the Maui Wildfire of 2023 for Equityand Environmental Justice (EEJ) issues. The proposed datasetaligns with the concepts of DCAI such as annotation quality,data preprocessing, privacy, feature engineering, governanceand provenance. We firmly believe that the proposed datasetwould lay a foundation to implement robust and reliable mod-ern AI algorithms for addressing EEJ issues.

Paridhi Parajuli↗
DOE OSTI2025

MultiTaskDeltaNet: change detection-based image segmentation for operando ETEM with application to carbon gasification kinetics

Transforming in situ transmission electron microscopy (TEM) imaging into a tool for spatially-resolved operando characterization of solid-state reactions requires automated, high-precision semantic segmentation of dynamically evolving features. However, traditional deep learning methods for semantic segmentation often face limitations due to the scarcity of labeled data, visually ambiguous features of interest, and scenarios involving small objects. To tackle these challenges, we introduce MultiTaskDeltaNet (MTDN), a novel deep learning architecture that creatively reconceptualizes the segmentation task as a change detection problem. By implementing a unique Siamese network with a U-Net backbone and using paired images to capture feature changes, MTDN effectively leverages minimal data to produce high-quality segmentations. Furthermore, MTDN utilizes a multi-task learning strategy to exploit correlations between physical features of interest. In an evaluation using data from in situ environmental TEM (ETEM) videos of filamentous carbon gasification, MTDN demonstrated a significant advantage over conventional segmentation models, particularly in accurately delineating fine structural features. Notably, MTDN achieved a 10.22% performance improvement over conventional segmentation models in predicting small and visually ambiguous physical features. This work bridges key gaps between deep learning and practical TEM image analysis, advancing automated characterization of nanomaterials in complex experimental settings.

08 HYDROGEN↗
NASA NTRS2023

A Global Land Cover Training Dataset From 1984 to 2020

State-of-the-art cloud computing platforms such as Google Earth Engine (GEE) enable regional-to-global land cover and land cover change mapping with machine learning algorithms. However, collection of high-quality training data, which is necessary for accurate land cover mapping, remains costly and labor-intensive. To address this need, we created a global database of nearly 2 million training units spanning the period from 1984 to 2020 for seven primary and nine secondary land cover classes. Our training data collection approach leveraged GEE and machine learning algorithms to ensure data quality and biogeographic representation. We sampled the spectral-temporal feature space from Landsat imagery to efficiently allocate training data across global ecoregions and incorporated publicly available and collaborator-provided datasets to our database. To reflect the underlying regional class distribution and post-disturbance landscapes, we strategically augmented the database. We used a machine learning-based cross-validation procedure to remove potentially mis-labeled training units. Our training database is relevant for a wide array of studies such as land cover change, agriculture, forestry, hydrology, urban development, among many others.

Radost Stanimirova↗
DOE OSTI2024

Hydra: Computer Vision for Data Quality Monitoring

Hydra: Computer Vision for Data Quality Monitoring Mar 13, 2024, 4:15 PM 30m Charles B. Wang Center, Stony Brook University Poster Track 1: Computing Technology for Physics Research Poster session with coffee break Speaker Ayan Roy Description Hydra is an extensible framework for training, managing, and deploying machine learning models for near real-time data quality monitoring. It is designed to take some of the burden off of shift crews by providing ‘round-the-clock’ monitoring of plots representing the data being collected. The Hydra system is backed by a database which is leveraged for near push button training and is primarily controlled and viewed through a set of web interfaces. This web interface contains a simple-to-use web based GUI for labeling of the datasets used in training; making it possible to label thousands of images quickly and efficiently. To aid in the analysis of Hydra inferences gradCAM, a method of interpretability, is performed and overlaid on the target image, highlighting regions of interest, making diagnosis of problems much faster. Development began in 2019 for the GlueX Experiment in Hall-D, the Hydra system has grown to encompass all of the experimental halls at Jefferson Laboratory. This talk will focus on the features of Hydra as well as provide details of the challenges present with deploying to disparate experimental halls. With a roadmap of development established, Hydra aims to continue to grow in richness of feature set and expand to encompass other monitoring tasks in differing communities.

Roy, Ayan↗
DOE OSTI2022

Photometric redshift estimation with convolutional neural networks and galaxy images: Case study of resolving biases in data-driven methods

Deep-learning models have been increasingly exploited in astrophysical studies, but these data-driven algorithms are prone to producing biased outputs that are detrimental for subsequent analyses. In this work, we investigate two main forms of biases: class-dependent residuals, and mode collapse. We do this in a case study, in which we estimate photometric redshift as a classification problem using convolutional neural networks (CNNs) trained with galaxy images and associated spectroscopic redshifts. We focus on point estimates and propose a set of consecutive steps for resolving the two biases based on CNN models, involving representation learning with multichannel outputs, balancing the training data, and leveraging soft labels. The residuals can be viewed as a function of spectroscopic redshift or photometric redshift, and the biases with respect to these two definitions are incompatible and should be treated individually. We suggest that a prerequisite for resolving biases in photometric space is resolving biases in spectroscopic space. Experiments show that our methods can better control biases than benchmark methods, and they are robust in various implementing and training conditions with high-quality data. Our methods hold promises for future cosmological surveys that require a good constraint of biases, and they may be applied to regression problems and other studies that make use of data-driven models. Nonetheless, the bias-variance tradeoff and the requirement of sufficient statistics suggest that we need better methods and optimized data usage strategies.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Mechanical Ventilation and Indoor Air Quality in Recently Constructed U.S. Homes in Marine and Cold-Dry Climates Data from Building America Project

Data were collected to characterize whole-house mechanical ventilation (WHMV) and indoor air quality (IAQ) in 55 homes in the Marine climate of Oregon and Cold-Dry climate of Colorado in the U.S. Sixteen homes were monitored for two weeks, with and without WHMV operating. Ventilation airflows; airtightness; time-resolved CO2, PM2.5 and radon; and time-integrated NO2, NOX and formaldehyde were measured. Participants provided information about IAQ-impacting activities, perceptions and ventilation use. All homes had operational cooktop ventilation and bathroom exhaust. Thirty homes had equipment that could meet the ASHRAE 62.2-2010 standard with continuous or controlled runtime and 34 had some WHMV operating as found. Thirty-five of 46 participants with WHMV reported they did not know how to operate it, and only half of the systems were properly labeled. Two-week homes had lower formaldehyde, radon, CO2, and NO (NOX-NO2) when operated with WHMV; and also had faster PM2.5 decays following indoor emission events. Overall IAQ satisfaction was similar in Oregon and Colorado, but more Colorado participants (19 vs. 3%) felt their IAQ could be improved and more reported dryness as a problem (58 vs. 14%). The collected data indicate that there are benefits of operating WHMV, even when continuous use may not be needed because outdoor pollutant concentrations are low and indoor sources do not present substantial challenges.

air quality↗
DOE OSTI2023

Automated Credibility Assessments of User Features in Scientific Software

Scientific software (SciSoft) is complex, often containing a mixture of production capabilities co-mingled with features under active research and development. Furthermore, SciSoft is often developed over decades by non-computer scientists who may not have a strong background in or prioritize software architecture design, testing, and quality (e.g., test coverage). These conditions lead to difficulty in understanding which software components or functions implement what user-facing features and therefore those features’ software quality pedigree. This lack of understanding poses challenges in assessing readiness and credibility of user features, and often relies on a SciSoft subject matter expert’s (SME) laborious investigation and assertion. This final report of a one-year Computing and Information Sciences Lab Directed Research and Development project presents a general framework for modeling SciSoft architecture as a direct relationship between user features and the software components/functions that implement them. Our approach leverages automated labeling of the SciSoft’s regression test suite and employs machine learning algorithms to construct the architecture model. We demonstrate this framework on the Solid Mechanics component of the SIERRA multi-physics engineering analysis suite developed at Sandia National Laboratories.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

AI Applications to Physics Experiments at Jefferson Lab

We survey how AI/ML is being deployed across Jefferson Lab's experimental and accelerator programs. In EPSCI, Hydra applies computer vision to automate real-time data-quality monitoring across all four experimental halls, replacing manual inspection of hundreds to thousands of histograms per shift. AIEC (AI Experiment Controls) uses ML to stabilize drift chamber gains and is now part of standard CEBAF production running, while AI Optimized Polarization (AIOP) targets autonomous control of polarized targets and photon beam angular alignment. In CASA, cavity fault classification models identify faulted cavities and trip types from waveform data with ~85% and ~78% agreement to labeled data, respectively, and are deployed in production; a separate effort applies LLMs and hybrid search to make the CEBAF operations logbook AI-ready. QCD-focused work includes transformer- and GAN-based generative models for particle-level event simulation, with distributed GAN training scaling studies on Polaris. Additional efforts span ML-on-FPGA for the EIC and a new Data Science Department coordinating anomaly detection, uncertainty quantification, and HPC-scalable ML lab-wide. Collectively, these projects illustrate AI's growing role in improving efficiency across JLab's nuclear physics mission.

Mei, Xinxin [Thomas Jefferson National Accelerator↗
DOE OSTI2025

Cleaned 5-Minute Resolution Air Quality and Meteorological Data from Nine TCEQ CAMS Sites in Houston, Texas (Nov 2021 – Oct 2022)

These data encompass 5-minute air monitoring and meteorological observations collected in the greater Houston, Texas metropolitan region, at nine (9) Continuous Ambient Monitoring Stations (CAMS) operated by the Texas Commission on Environmental Quality (TCEQ) between November 1, 2021 and October 31, 2022. The CAMS sites (CAMS 1, 8, 35, 45, 148, 403, 405, 410, and 1052) were chosen because their instrumentation includes measurements of PM2.5. These sites also provide continuous multi-parameter air-quality and meteorological measurements. Particulate matter (PM2.5, PM10) was sampled along with several trace gases, including ozone (O3), nitrogen oxides (NO, NO2, NOx), sulfur dioxide (SO2), and carbon monoxide (CO). The data set also contains standard surface meteorological parameters (temperature, humidity, pressure, wind speed, and wind direction). Several sites also include AutoGC-based measurements of volatile organic compounds (VOCs). Air monitoring instruments deployed at the selected sites comprise the following systems: BAM-1020 or TEOM (PM2.5), Thermo Scientific TEI 49i (O3), TEI 42i (NOx), and AutoGCs (VOCs). This data set is similar to the data included within the houairq5mX1.00 datastream, except for a few additional quality control steps. A systematic data cleaning and verification process was performed on the data set to ensure its quality and preparation for analysis. Removal of non-numeric status flags (e.g., [LIM], [QAS], [SPZ], [CAL], [PMA], [AQI], [SPN], [MAL]) was accomplished by employing rule-based string parsing to extract valid numerical values. Missing entries were set to -9999; however, invalid or anomalous values (e.g., 99999) were retained as originally reported by the TCEQ to preserve data provenance. The time sequence was verified for completeness, removal of duplicates, and uniformity at 5-minute intervals. Column labeling was standardized, and corresponding values were assessed for physical plausibility. All timestamps in the data set were reported in Coordinated Universal Time (UTC) as provided by the TCEQ. Further, the latitude and longitude coordinates were added for each CAMS site. A subset of the data (June 1–September 30, 2022) has been used in the following publication: Subba et al. 2025. “Implications of sea breeze circulations on boundary layer aerosols in the southern coastal Texas region.” EGUsphere 2025: 1–49, https://doi.org/10.5194/egusphere-2025-2659.

latitude↗